Xiangyu Yue

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

2023 · arXiv (Cornell University)

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Language-Image Pre-training (CLIP) model, we observe that the model's …

Towards Unified and Effective Domain Generalization

2023 · arXiv (Cornell University)

We propose $\textbf{UniDG}$, a novel and $\textbf{Uni}$fied framework for $\textbf{D}$omain $\textbf{G}$eneralization that is capable of significantly enhancing the out-of-distribution generalization performance of foundation models regardless of their architectures. The core idea of UniDG is to …